Nemotron 3 Ultra now available on AI Gateway

Nvidia's Nemotron 3 Ultra, an open Mixture-of-Experts reasoning model with a 1M token context window, is now available on Vercel AI Gateway. The model is designed for long-running agent workflows, offering up to 350 tokens per second throughput and up to 30% lower cost on agentic tasks. AI Gateway provides a unified API for the model with features including custom reporting, zero data retention, and dynamic provider sorting by latency and cost.

Nemotron 3 Ultra from Nvidia is now available on Vercel AI Gateway https://vercel.com/ai-gateway . Nemotron 3 Ultra is an open Mixture-of-Experts reasoning model built for orchestrating long-running agent workflows, with a 1M token context window. The model targets multi-turn agent workflows: planning, tool use, sub-agent delegation, and error recovery. Throughput reaches up to 350 tokens per second, with up to 30% lower cost on agentic tasks. To use Nemotron 3 Ultra, set model to nvidia/nemotron-3-ultra-550b-a55b in the AI SDK https://ai-sdk.dev/ . AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting https://vercel.com/changelog/custom-reporting-ai-gateway , Zero Data Retention support https://vercel.com/blog/zdr-on-ai-gateway , dynamic provider sorting by latency and cost https://vercel.com/changelog/sort-providers-by-cost-latency-or-throughput-on-ai-gateway , and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key https://vercel.com/docs/ai-gateway bring-your-own-key BYOK requests. Learn more about AI Gateway https://vercel.com/docs/ai-gateway , view the AI Gateway model leaderboard https://vercel.com/ai-gateway/leaderboards or try it in our model playground https://vercel.com/ai-gateway/models/nemotron-3-ultra-550b-a55b .